README.md

metadata

library_name: transformers
license: llama3.1
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
tags:
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3
    results: []

engineer-heavy-500k-barc-llama3.1-8b-ins-fft-induction_lr1e-5_epoch3

This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2710

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• total_train_batch_size: 128
• total_eval_batch_size: 128
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss
0.2797	1.0	2995	0.2817
0.2389	2.0	5990	0.2710

Framework versions

• Transformers 4.45.0.dev0
• Pytorch 2.4.0
• Datasets 3.1.0
• Tokenizers 0.19.1